scholarly journals Atlantic Hurricane Activity Prediction: A Machine Learning Approach

Atmosphere ◽  
2021 ◽  
Vol 12 (4) ◽  
pp. 455
Author(s):  
Tanmay Asthana ◽  
Hamid Krim ◽  
Xia Sun ◽  
Siddharth Roheda ◽  
Lian Xie
Keyword(s):  
Machine Learning ◽  
Environmental Damage ◽  
Activity Prediction ◽  
Sea Level Pressure ◽  
Atlantic Hurricane ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Non Linear ◽  
Hurricane Activity

Long-term hurricane predictions have been of acute interest in order to protect the community from the loss of lives, and environmental damage. Such predictions help by providing an early warning guidance for any proper precaution and planning. In this paper, we present a machine learning model capable of making good preseason-prediction of Atlantic hurricane activity. The development of this model entails a judicious and non-linear fusion of various data modalities such as sea-level pressure (SLP), sea surface temperature (SST), and wind. A Convolutional Neural Network (CNN) was utilized as a feature extractor for each data modality. This is followed by a feature level fusion to achieve a proper inference. This highly non-linear model was further shown to have the potential to make skillful predictions up to 18 months in advance.

scholarly journals A machine learning approach to predicting short-term mortality risk in patients starting chemotherapy

2017 ◽  
Author(s):  
Aymen A. Elfiky ◽  
Maximilian J. Pany ◽  
Ravi B. Parikh ◽  
Ziad Obermeyer
Keyword(s):  
Machine Learning ◽  
Mortality Risk ◽  
Palliative Chemotherapy ◽  
Learning Algorithm ◽  
Cancer Center ◽  
Short Term ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Short Term Mortality ◽  
And Performance

ABSTRACTBackgroundCancer patients who die soon after starting chemotherapy incur costs of treatment without benefits. Accurately predicting mortality risk from chemotherapy is important, but few patient data-driven tools exist. We sought to create and validate a machine learning model predicting mortality for patients starting new chemotherapy.MethodsWe obtained electronic health records for patients treated at a large cancer center (26,946 patients; 51,774 new regimens) over 2004-14, linked to Social Security data for date of death. The model was derived using 2004-11 data, and performance measured on non-overlapping 2012-14 data.Findings30-day mortality from chemotherapy start was 2.1%. Common cancers included breast (21.1%), colorectal (19.3%), and lung (18.0%). Model predictions were accurate for all patients (AUC 0.94). Predictions for patients starting palliative chemotherapy (46.6% of regimens), for whom prognosis is particularly important, remained highly accurate (AUC 0.92). To illustrate model discrimination, we ranked patients initiating palliative chemotherapy by model-predicted mortality risk, and calculated observed mortality by risk decile. 30-day mortality in the highest-risk decile was 22.6%; in the lowest-risk decile, no patients died. Predictions remained accurate across all primary cancers, stages, and chemotherapies—even for clinical trial regimens that first appeared in years after the model was trained (AUC 0.94). The model also performed well for prediction of 180-day mortality (AUC 0.87; mortality 74.8% in the highest risk decile vs. 0.2% in the lowest). Predictions were more accurate than data from randomized trials of individual chemotherapies, or SEER estimates.InterpretationA machine learning algorithm accurately predicted short-term mortality in patients starting chemotherapy using EHR data. Further research is necessary to determine generalizability and the feasibility of applying this algorithm in clinical settings.

scholarly journals Machine Learning Approach to Quantity Management for Long-Term Sustainable Development of Dockless Public Bike: Case of Shenzhen in China

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Qingfeng Zhou ◽  
Chun Janice Wong ◽  
Xian Su
Keyword(s):  
Machine Learning ◽  
Sustainable Development ◽  
Clustering Algorithms ◽  
Utilization Efficiency ◽  
Impact Factors ◽  
Classification Algorithms ◽  
Learning Approach ◽  
High Efficient ◽  
Machine Learning Approach

Since the number of bicycles is critical to the sustainable development of dockless PBS, this research practiced the introduction of a machine learning approach to quantity management using OFO bike operation data in Shenzhen. First, two clustering algorithms were used to identify the bicycle gathering area, and the available bike number and coefficient of available bike number variation were analyzed in each bicycle gathering area’s type. Second, five classification algorithms were compared in the accuracy of distinguishing the type of bicycle gathering areas using 25 impact factors. Finally, the application of the knowledge gained from the existing dockless bicycle operation data to guide the number planning and management of public bicycles was explored. We found the following. (1) There were 492 OFO bicycle gathering areas that can be divided into four types: high inefficient, normal inefficient, high efficient, and normal efficient. The high inefficient and normal inefficient areas gathered about 110,000 bicycles with low usage. (2) More types of bicycle gathering area will affect the accuracy of the classification algorithm. The random forest classification had the best performance in identifying bicycle gathering area types in five classification algorithms with an accuracy of more than 75%. (3) There were obvious differences in the characteristics of 25 impact factors in four types of bicycle gathering areas. It is feasible to use these factors to predict area type to optimize the number of available bicycles, reduce operating costs, and improve utilization efficiency. This work helps operators and government understand the characteristics of dockless PBS and contributes to promoting long-term sustainable development of the system through a machine learning approach.

scholarly journals Modeling of apartment prices in a Colombian context from a machine learning approach with stable-important attributes

DYNA ◽  
2020 ◽  
Vol 87 (212) ◽  
pp. 63-72
Author(s):  
Jorge Iván Pérez Rave ◽  
Favián González Echavarría ◽  
Juan Carlos Correa Morales
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Learning Approach ◽  
Predictive Capability ◽  
Predictive Capacity ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Property Price ◽  
Object Of Study ◽  
Online Pricing

The objective of this work is to develop a machine learning model for online pricing of apartments in a Colombian context. This article addresses three aspects: i) it compares the predictive capacity of linear regression, regression trees, random forest and bagging; ii) it studies the effect of a group of text attributes on the predictive capability of the models; and iii) it identifies the more stable-important attributes and interprets them from an inferential perspective to better understand the object of study. The sample consists of 15,177 observations of real estate. The methods of assembly (random forest and bagging) show predictive superiority with respect to others. The attributes derived from the text had a significant relationship with the property price (on a log scale). However, their contribution to the predictive capacity was almost nil, since four different attributes achieved highly accurate predictions and remained stable when the sample change.

A machine learning approach for the automatic long-term structural health monitoring

2018 ◽  
Vol 18 (3) ◽  
pp. 819-837 ◽  
Author(s):  
Giacomo Vincenzo Demarie ◽  
Donato Sabia
Keyword(s):  
Machine Learning ◽  
Data Acquisition ◽  
Structural Behavior ◽  
Practical Applications ◽  
Existing Structures ◽  
Machine Learning Approach ◽  
Modes Of Vibration ◽  
Engineering Parameters ◽  
Over Time

Measuring the response of a structure to the ambient and service loads is a source of information that can be used to estimate some important engineering parameters or, to a certain extent, to characterize the structural behavior as a whole. By repeating the data acquisition over a period of time, it is possible to check for variations in the structure’s response, which may be correlated to the appearance or growth of a damage (e.g. following some exceptional event as the earthquake, or as a consequence of materials and components aging). The complexity of some existing structures and their environment very often requires the execution of a monitoring plan in order to support analyses and decisions through the evidence of measured data. If the monitoring is implemented through a sensor network continuously acquiring over time, then the evolution of the structural behavior may be tracked continuously as well. Such approach has become a viable option for practical applications since the last decade, as a consequence of the progress in the data acquisition and storage systems. However, proper methods and algorithms are needed for managing the large amount of data and the extraction of valuable knowledge from it. This article presents a methodology aimed at making automatic the process of structural monitoring in case it is carried continuously over time. It relies on some existing methods from the machine learning and data mining fields, which are casted into a process targeted to delimit the need of the human being intervention to the training phase and the engineering judgment of the results. The methodology has been successfully applied to the real-world case of an ancient masonry bell tower, the Ghirlandina Tower (Modena, Italy), where a network made of 12 accelerometers and 3 thermocouples has been acquiring continuously since August 2012. The structural characterization is performed by identifying the first modes of vibration, whose evolution over time has been tracked.

Machine learning model for feature recognition of sports competition based on improved TLD algorithm

2020 ◽  
pp. 1-12
Author(s):  
Qinglong Ding ◽  
Zhenfeng Ding
Keyword(s):  
Machine Learning ◽  
Feature Recognition ◽  
Experimental Results ◽  
Pedestrian Tracking ◽  
Data Set ◽  
Recognition Model ◽  
Standard Data ◽  
Machine Learning Model ◽  
Environmental Background

Sports competition characteristics play an important role in judging the fairness of the game and improving the skills of the athletes. At present, the feature recognition of sports competition is affected by the environmental background, which causes problems in feature recognition. In order to improve the effect of feature recognition of sports competition, this study improves the TLD algorithm, and uses machine learning to build a feature recognition model of sports competition based on the improved TLD algorithm. Moreover, this study applies the TLD algorithm to the long-term pedestrian tracking of PTZ cameras. In view of the shortcomings of the TLD algorithm, this study improves the TLD algorithm. In addition, the improved TLD algorithm is experimentally analyzed on a standard data set, and the improved TLD algorithm is experimentally verified. Finally, the experimental results are visually represented by mathematical statistics methods. The research shows that the method proposed by this paper has certain effects.

scholarly journals Forecasting Internally Displaced Population Migration Patterns in Syria and Yemen

2019 ◽  
Vol 14 (3) ◽  
pp. 302-307
Author(s):  
Benjamin Q. Huynh ◽  
Sanjay Basu
Keyword(s):  
Machine Learning ◽  
Food Prices ◽  
Internally Displaced ◽  
Fuel Prices ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Using Data ◽  
Diverse Data ◽  
Internally Displaced Population ◽  
Persistence Model

ABSTRACTObjectives:Armed conflict has contributed to an unprecedented number of internally displaced persons (IDPs), individuals who are forced out of their homes but remain within their country. IDPs often urgently require shelter, food, and healthcare, yet prediction of when IDPs will migrate to an area remains a major challenge for aid delivery organizations. We sought to develop an IDP migration forecasting framework that could empower humanitarian aid groups to more effectively allocate resources during conflicts.Methods:We modeled monthly IDP migration between provinces within Syria and within Yemen using data on food prices, fuel prices, wages, location, time, and conflict reports. We compared machine learning methods with baseline persistence methods of forecasting.Results:We found a machine learning approach that more accurately forecast migration trends than baseline persistence methods. A random forest model outperformed the best persistence model in terms of root mean square error of log migration by 26% and 17% for the Syria and Yemen datasets, respectively.Conclusions:Integrating diverse data sources into a machine learning model appears to improve IDP migration prediction. Further work should examine whether implementation of such models can enable proactive aid allocation for IDPs in anticipation of forecast arrivals.

Improving Multiseason Forecasts of North Atlantic Hurricane Activity

2008 ◽  
Vol 21 (6) ◽  
pp. 1209-1219 ◽  
Author(s):  
James B. Elsner ◽  
Thomas H. Jagger ◽  
Michael Dickinson ◽  
Dail Rowe
Keyword(s):  
North Atlantic ◽  
Monte Carlo Sampling ◽  
Sea Surface ◽  
Economic Losses ◽  
Atlantic Hurricane ◽  
Time Period ◽  
Hurricane Season ◽  
Hurricane Activity ◽  
Term Management

Abstract Hurricanes cause drastic social problems as well as generate huge economic losses. A reliable forecast of the level of hurricane activity covering the next several seasons has the potential to mitigate against such losses through improvements in preparedness and insurance mechanisms. Here a statistical algorithm is developed to predict North Atlantic hurricane activity out to 5 yr. The algorithm has two components: a time series model to forecast average hurricane-season Atlantic sea surface temperature (SST), and a regression model to forecast the hurricane rate given the predicted SST value. The algorithm uses Monte Carlo sampling to generate distributions for the predicted SST and model coefficients. For a given forecast year, a predicted hurricane count is conditional on a sampled predicted value of Atlantic SST. Thus forecasts are samples of hurricane counts for each future year. Model skill is evaluated over the period 1997–2005 and compared against climatology, persistence, and other multiseasonal forecasts issued during this time period. Results indicate that the algorithm will likely improve on earlier efforts and perhaps carry enough skill to be useful in the long-term management of hurricane risk.

Sign in / Sign up

Export Citation Format

Share Document